Nano Banana

Verified against Nano Banana / Gemini 3.1 Flash Image · 2026-07-25

Shoot appetizing menu photography for a delivery app listing

A food-photography brief tuned for how delivery-app thumbnails actually get judged — steam, glisten, and garnish freshness cues specified explicitly, since those are the details that separate an appetizing shot from a merely accurate one.

Nano Banana (Gemini 3.1 Flash Image)Gemini app6 fillable variables

The prompt

Ready to copy — highlighted parts are example details you can swap.

Act as a food photographer shooting a dish for a delivery-app menu listing. The image needs to look appetizing enough to drive an order decision within the one or two seconds a scrolling user actually spends looking at it.

DISH
a stacked beef birria taco trio, cheese-crisped edges, served with a small side cup of consommé.

PLATING AND GARNISH
tacos fanned slightly on a dark slate plate, garnished with chopped white onion, cilantro, and a lime wedge. Garnish should look freshly placed — herbs with visible texture and slight moisture, no wilting, no garnish that looks like it's been sitting for more than a minute or two under the lights.

SURFACE AND PROPS
a dark, slightly textured wood table, with a folded linen napkin and one small dish of extra consommé just at the edge of frame. Keep props minimal and secondary — this is a shot of the dish, not a styled tablescape, so anything in frame besides the plate itself should read as supporting context, not compete for attention.

LIGHTING SETUP
soft window-style light from the upper left, a small reflector card to the right to keep shadows from going too dark on that side. Food photography lives or dies on how light catches moisture and fat — render glossy sauces and glazes with a genuine specular highlight where the light source would actually catch them, not a flat, matte render that makes a sauce look dry.

CAMERA ANGLE
a 45-degree three-quarter angle, close enough to see the cheese-crisped taco edges clearly. Choose the angle that best shows this specific dish's most appetizing feature — a layered dish often reads better from a slight three-quarter angle that reveals its cross-section or layers, while a flat dish like a pizza or a bowl arrangement often reads better shot closer to top-down.

FRESHNESS AND TEMPERATURE CUES
a thin wisp of steam rising from the consommé cup, since it should read as served hot. If steam is called for, render it as thin, translucent wisps rising naturally from the dish's actual hottest visible point, not a thick, uniform fog covering the whole plate — real steam from real food is wispy and uneven, not a special-effects cloud.

COLOR AND CONTRAST
Keep the dish's real colors true to what the ingredients would actually look like — don't oversaturate sauces or proteins into an unnatural color that would look like a mismatch when the food actually arrives at someone's door. A menu photo that oversells the dish's color creates the exact customer disappointment that drives poor reviews and refund requests.

WHAT TO KEEP OUT OF FRAME
No hands, no cutlery unless specifically part of the styling brief, no visible restaurant branding beyond what's naturally part of the plateware, no text overlays — this is a clean photographic asset, not a finished ad.

OUTPUT
One image, cropped and lit to work as a thumbnail-sized delivery-app listing photo — bold enough to read clearly even at a small display size, accurate enough that it matches what actually gets delivered.

Customize

Optional — swap in your own details for the highlighted parts above.

Why this works

Delivery-app browsing behavior is genuinely different from a sit-down menu: a user scrolling a results feed spends a very short window deciding whether a thumbnail is worth tapping, which is why this brief front-loads the single most appetite-driving visual cue for the specific dish — a cross-section for a layered item, a top-down view for a bowl — rather than defaulting to one generic "food photo" angle regardless of what the dish actually is, since the angle that sells a burger and the angle that sells a poke bowl are genuinely different and a one-size-fits-all instruction leaves that choice to chance. Second, the steam-as-wisps instruction targets a specific and recognizable AI-food-photo tell: models asked for "steam rising from the food" without more guidance frequently render a thick, uniform fog effect that looks like a stock photo overlay rather than real steam, which real steam never actually looks like — it's uneven, thin, and rises from the specific hottest point on a dish, not blanketing the whole plate, and naming that physical behavior explicitly steers the model away from the generic effect toward the physically grounded one its real-photography training data actually supports. Third, the color-accuracy constraint exists because food photography carries a business risk generic product photography mostly doesn't: an oversaturated, unrealistically vibrant menu photo drives the order, but the customer compares the delivered dish to that exact photo within minutes of it arriving, and a visible color mismatch — a sauce that looked deep red in the photo but is actually a muted brown-red in reality — is a documented, specific driver of delivery-app complaints and refund requests, which is why this brief explicitly trades a small amount of visual drama for accuracy that survives the moment of actual delivery.

Verified against

Nano Banana / Gemini 3.1 Flash Image Gemini 3.1 Flash Image · 2026-07-25

Changelog

  • 2026-07-25 Initial publish, verified against Nano Banana (Gemini 3.1 Flash Image) on a birria taco delivery-app listing shot.

Need this built into your business?

If a prompt isn't enough — what Scult builds, built and maintained for you — that's Scult's day job.

EXPLORE WHAT SCULT BUILDS
Shoot a catalog-ready e-commerce product photo with Nano BananaA full studio-photography brief for Nano Banana (Gemini 3.1 Flash Image) — material, surface, lighting rig, and angle specified separately so the model renders accurate reflections and shadow behavior instead of a generic glossy render.Nano Banana (Gemini 3.1 Flash Image)Gemini app2026-07-20Turn a hex palette into a brand mood-board flat-lay with Nano BananaA composited overhead flat-lay brief that locks every object and surface in the frame to an exact hex palette — the natural next step after generating a palette with the Colour Palette Generator, built for Nano Banana's literal reading of pasted color codes.Nano Banana (Gemini 3.1 Flash Image)Gemini app2026-07-21Make one surgical edit to a photo without touching anything elseA conversational edit instruction for an uploaded photo that isolates exactly one change and explicitly locks everything else — lighting, pose, background, composition — so Nano Banana's edit doesn't quietly redraw the whole frame.Nano Banana (Gemini 3.1 Flash Image)Gemini app2026-07-21Keep one character consistent across a set of different scenesLocks a defined character's face, proportions, and defining features across a run of separately-described scenes in the same Nano Banana conversation, instead of letting each new generation quietly redesign the character.Nano Banana (Gemini 3.1 Flash Image)Gemini app2026-07-22
All Nano Banana prompts

Check your AI visibility

One URL in, a 0–100 score and the exact fixes out.

RUN THE CHECK

Browse all the tools

15 tools across six categories
13 of them never send your data anywhere

Free · No signup · No trial clock

SEE THE DIRECTORY